A new tool for the evaluation of the rehabilitation outcomes in older persons: a machine learning model to predict functional status 1 year ahead.

PURPOSE: To date, the assessment of disability in older people is obtained utilizing a Comprehensive Geriatric Assessment (CGA). However, it is often difficult to understand which areas of CGA are most predictive of the disability. The aim of this study is to evaluate the possibility to early predict-1 year ahead-the disability level of a patient using machine leaning models. METHODS: Community-dwelling older people were enrolled in this study. CGA was made at baseline and at 1 year follow-up. After collecting input/independent variables (i.e., age, gender, schooling followed, body mass index, information on smoking, polypharmacy, functional status, cognitive performance, depression, nutritional status), we performed two distinct Support Vector Machine models (SVMs) able to predict functional status 1 year ahead. To validate the choice of the model, the results achieved with the SVMs were compared with the output produced by simple linear regression models. RESULTS: 218 patients (mean age = 78.01; SD = 7.85; male = 39%) were recruited. The combination of the two SVMs is able to achieve a higher prediction accuracy (exceeding 80% instances correctly classified vs 67% instances correctly classified by the combination of the two linear regression models). Furthermore, SVMs are able to classify both the three categories, self sufficiently, disability risk and disability, while linear regression model separates the population only in two groups (self-sufficiency and disability) without identifying the intermediate category (disability risk) which turns out to be the most critical one. CONCLUSIONS: The development of such a model can contribute to the early detection of patients at risk of self-sufficiency loss.

Association between serum vitamin D and metabolic syndrome in middle-aged and older adults and role of supplementation therapy with vitamin D.

OBJECTIVES: To evaluate i) the correlation between vitamin D (vit. D) serum concentrations and metabolic syndrome (MetS); ii) the efficacy of 6 months supplementation therapy with vit. D. METHOD: 200 patients were enrolled. Blood analyses and anthropometric measurements were carried out. Patients with hypovitaminosis D received an oral supplement therapy. RESULTS: 81% of the sample shows vit. D levels < 30 ng/mL. Rate of MetS was significantly higher in vit. D deficiency group than in vit D insufficiency (p = 0.009) and sufficiency (p = 0.002) groups. Vit. D shows a significant negative correlation with both waist circumference (WC) (ρ - 0.202 p = 0.004) and glycaemia values (FBG) (ρ -0.185 p = 0.009). After the supplementation therapy in a group of 60 subjects a significant increase in vit. D levels (p = 0.001) and a significant reduction in WC values (p = 0.001) were observed. CONCLUSIONS: MetS, WC and FBG appeared to be associated vit. D status and it is well-known that central obesity, with the inflammatory alterations thereto correlated that determine insulin resistance, can be considered the "primum movens" for the development of MetS.

Relationship between vitamin D and body fat distribution evaluated by DXA in postmenopausal women.

OBJECTIVE: The aim of this study was to explore the relationship between 25-hydroxyvitamin D (25[OH]D) serum concentrations and body fat distribution in a sample of postmenopausal women. METHODS: We enrolled sixty-two postmenopausal women; 25(OH)D serum concentrations, serum intact parathyroid hormone, blood analyses, and anthropometric measurements were carried out. Body fat composition was evaluated by dual-energy X-ray absorptiometry. Insulin resistance was estimated by homeostatic model assessment of insulin resistance (HOMA-IR) calculation. RESULTS: Low levels of vitamin D (<30 ng/mL) were found in 77.4% of the population studied. There was a correlation (P < 0.0001) between 25(OH)D and waist circumference (r = -0.543), android fat to gynoid fat (A/G) ratio (r = -0.554), high-density lipoprotein cholesterol (r = 0.498), and HOMA-IR (r = -0.520). A/G fat ratio (B = -34.90; 95% confidence interval [-55.30, -14.1]; P = 0.019), HOMA-IR (B = -3.17; 95% confidence interval [-5.99, -0.351]; P = 0.028), and high-density lipoprotein cholesterol (B = 0.361; 95% confidence interval [0.033, 0.698]; P = 0.032), were found to be independent predictors of lower 25(OH)D by multilogistic regression analysis. Except for waist circumference, both these results were maintained when correlations were adjusted for age, onset of menopause, serum intact parathyroid hormone, and medications, and when body mass index was added as covariate. CONCLUSIONS: Vitamin D deficiency and insufficiency are common conditions. A/G ratio appeared to be associated with 25(OH)D concentrations and it is well-known that the android disposition of body fat is more closely associated with the onset of metabolic syndrome. Longitudinal studies are needed to better characterize the direction and the causal links of this association.

The influence of lifestyle on cardiovascular risk factors. Analysis using a neural network.

The cardiovascular pathologies are the most common causes of death in the elderly patient. To single out the main risk factors in order to effectively prevent the onset of the disease, the authors experimented a special computerized tool, the neural network, that works out a mathematical relation that can obtain certain data (defined as output) as a function of other data (defined as input). Data were processed from a sample of 276 subjects of both sexes aged 26-69 years old. The output data were: high/low cholesterolemia, HDL cholesterol, triglyceridemia with respect to an established cut-off; the input data were: sex, age, build, weight, married/single, number of children, number of cigarettes smoked/day, amount of wine and number of cups of coffee. We conclude that: (i) a relationship exists, deduced from a neural network, between a set of input variables and a dichotomous output variable; (ii) this relationship can be expressed as a mathematical function; (iii) a neural network, having learned the data on a sufficiently large population, can provide valid predictive data for a single individual with a high probability (up to 93.33%) that the response it gives is correct. In this study, such a result is found for two of the three cardiovascular risk indicators considered (cholesterol and triglycerides); (iv) the repetition of the neural network analysis of the cases in question after a "pruning" operation provided a somewhat less good performance; (v) a statistical analysis conducted on those same cases has confirmed the existence of a strong relationship between the input and the output variables. Therefore the neural network is a valid instrument for providing predictive in a single subject on cardiovascular pathology risks.

Myocardial cytoprotection by trimetazidine against anthracycline-induced cardiotoxicity in anticancer chemotherapy.

The ability of trimetazidine (2,3,4, trimethoxybenzylpiperazine dihydrochloride, TMZ) to protect the myocardium against anthracycline (ANT)-induced cardiotoxicity during chemotherapy has been evaluated in female patients with breast cancer. A clinical trial was conducted in 61 patients subdivided into three groups: group 1 (n = 15, G1 ) treated with standard ANT protocol and cardioprotection by dexrazoxane (DEX) plus TMZ (60 mg, daily dose); group 2 (n = 22, G2) treated with ANT and cardioprotection by TMZ only; and group 3 (n = 24, G3) scheduled to receive ANT therapy and DEX. All the patients submitted to an echocardiographic evaluation of diastolic function (E wave velocity, A wave velocity, isovolumetric relaxation time [IVRT], deceleration time [DT]) at enrollment (T0), at T1 time, at T2 time, and at T3 time. After a 12-month follow-up period, the patients showed a good conservation of diastolic function both in G1 and G2 groups. No statistically significant difference was observed in E wave and A wave velocity and E/A ratio after ANT treatment. TMZ produced a cardioprotective effect, comparable to DEX protection, against subacute and chronic subclinical cardiotoxicity with no significant changes in diastolic function after 1 year of follow-up.

Empirical antibiotic therapy (ABT) of lower respiratory tract infections (LRTI) in the elderly: application of artificial neural network (ANN). Preliminary results.

LRTI are among the most common diseases in developed countries, including chronic obstructive pulmonary disease (COPD), one of the most frequent conditions. Their treatment in general practice is often unsuccessful and this increases hospital admissions. We know, bacterial infections in the elderly show a higher morbidity and mortality, either for more severe symptoms, than in younger adults, or because the causing agent often remains unknown. The need for a quick initiation of ABT often requires to chose on empirical grounds. To date there are no official guidelines for empirical ABT of COPD exacerbations, but only heterogeneous and often conflicting recommendations exist. The aim of our study was to identify a tool to guide the choice of the most effective empirical ABT when symptoms are acute and bacteriological tests cannot be performed. We used an ANN to study 117 patients aged between 55 and 97 years (mean 81.5 ± 8.7 years) (± S.D.), admitted with a diagnosis of pneumonia, COPD exacerbation or pneumonia with respiratory failure. We registered symptoms at onset and some individual variables such as age, sex, risk factors, comorbidity, current drug therapies. Then the ANN was applied to choose ABT in 20 patients versus 20 subjects whose therapy was chosen by the physicians, comparing these groups for therapy's efficacy, mean durations of therapy and hospitalization (H). In the learning phase, the ANN could predict the resolution index 99.05% of the time (i.e., 104 times) with a ± S.D. = 0.23. After the training, during the test phase, the network predicted the resolution index 91.67% of the time (i.e., 11 times) with a ± S.D. = 0.54, thus proving the validity of the relations identified during the learning phase. Preliminary results of the application of our tool, show the ANN allowed us to greatly reduce the duration of the ABT and subsequently of the H. Based on preliminary results, we assume that the use of ANN can make a valuable contribution in the choice of empirical ABT in the course of acute lung diseases in elderly.

The Mozart effect in patients suffering from tinnitus.

CONCLUSION: The study suggests that Mozart therapy could be a valid alternative to the common sound therapy methods in tinnitus patients. OBJECTIVES: The aim of the study was to evaluate the presence of the Mozart effect as indexed by a variation in tinnitus intensity and tolerability. METHOD: Sixty-two individuals aged between 22 and 78 years, reporting tinnitus for at least 1 year, were enrolled for the study. All patients attended a 1 h cognitive behavioral counseling session and listened to Mozart's sonata k448 for 1 h per day for a month. Afterwards patients listened to Beethoven's Für Elise sonata for 1 h per day for a month. To evaluate the general stress level, the impact of tinnitus on patients' quality of life, and the intensity of tinnitus, patients were invited to participate in three tests: the Measure du Stress Psychologique (MSP) questionnaire, the Tinnitus Handicap Inventory (THI), and a 0 to 10 visual analog scale (VAS). RESULTS: For all the parameters investigated, MSP, THI, and intensity, there was a general significant improvement between the pre- and post-listening evaluation. A significant improvement, as regards THI and intensity, could already be appreciated after a single exposure to Mozart's sonata.

Montelukast therapy and psychological distress in chronic obstructive pulmonary disease (COPD): a preliminary report.

Chronic obstructive pulmonary disease (COPD) is an alteration in which ventilatory function, exercise capacity and health status of patients progressively decline and it is characterized by an increase of inflammatory cytokines such as TNF-α, LTB4, IL-8, etc. In this study we considered twenty patients (15 males and 5 females; mean age: 72.8 ± 6.3) with stable COPD. All patients were performed evaluation of psychological stress at enrollment and were treated with leukotriene receptor antagonists (montelukast tablets) 10mg/day for 12 months. After 12 months we observed a significant decrease of serum levels of LTB4, IL-8 and also a decrease of the number of outpatient clinic visits, of the number of hospitalizations and of the duration of hospitalization.